AI Risk Systems Architect

Grab; Singapore; On-site; SGD 150,000 - 210,000; Full time

Benefits offered by this job

Term Life Insurance

Medical Insurance

GrabFlex benefits

Parental and Birthday leave

LASA volunteering leave

Grabber Assistance Programme

FlexWork arrangements

Job summary

Grab is seeking a senior backend/data engineer to join the Integrity team, focusing on architecting AI data infrastructure, building multi-agent workflows, and integrating Trust & Safety logic with the real-time Risk Engine.

You will optimize reliability, performance, and costs while collaborating with Data Analysts to translate domain knowledge into scalable agent capabilities using LangSmith, LangGraph, and modern orchestration frameworks.

Qualifications

• 6+ years of experience in data-heavy systems or backend engineering.
• Proficiency in Python and backend architecture.
• Strong data engineering fundamentals (ETL, pipelines, vectorization, embeddings).
• Experience deploying LLMs with LangSmith / LangGraph is preferred.

Responsibilities

• Architect the AI data infrastructure: data ingestion pipelines, vector databases, embeddings, and parsing unstructured data to enrich agent knowledge base.
• Design, deploy, and maintain end-to-end multi-agent systems using modern orchestration frameworks to automate risk detection workflows.
• Implement automated guardrails to block hallucinated AI-generated SQL or rules before production.
• Build MCP servers and restricted API wrappers that safely connect AI agents to Grab's Risk Engine.
• Improve reliability and reduce token costs for internal agent platforms while preserving production stability.
• Collaborate with Data Analysts to translate domain knowledge into machine-readable formats and scalable agent skills.

Skills

Python

Backend engineering

Data engineering

Machine learning

Education

Bachelor's Degree in Computer Science / Data Engineering / Analytics

Tools

LangSmith

LangGraph

Job description

Grab is seeking a senior backend/data engineer to join the Integrity team, focusing on architecting AI data infrastructure, building multi-agent workflows, and integrating Trust & Safety logic with the real-time Risk Engine.

You will optimize reliability, performance, and costs while collaborating with Data Analysts to translate domain knowledge into scalable agent capabilities using LangSmith, LangGraph, and modern orchestration frameworks.